A minimax robust learning framework for uncertainty-aware indoor localization in LoRaWAN networks using adaptive signal filtering and environmental intelligence
Keywords:
Minimax estimation, robust filtering, indoor localization, LoRaWAN, adaptive filtering, uncertainty quantification.Abstract
LoRaWAN is increasingly used for indoor Internet-of-Things sensing, but its received signal strength indicator (RSSI) is heavily perturbed by multipath, human blockage, wall structure, and microclimate dynamics, so ranging methods built only to minimize average error give no guarantee about the worst case. This paper treats indoor LoRaWAN ranging as a minimax robust estimation problem. We couple an environment-aware multi-wall path-loss model with a Minimax Robust Adaptive Filter (MRAF), which applies a Huber-type bounded-influence correction to the RSSI innovation together with an environmentally driven process-noise schedule, and we prove that the resulting one-step innovation risk stays bounded over an epsilon-contamination neighborhood of the nominal noise model, unlike the corresponding unbounded Kalman correction. The framework is tested on 1,715,869 aggregated uplinks collected over roughly eight months from six statically deployed end devices, 8 to 40 meters from a single gateway, with 0 to 2 concrete walls and 0 to 5 wooden walls per link. Against raw RSSI, a moving-average filter, and a standard Kalman filter, the proposed method reduces mean ranging RMSE from 92.0 m to 8.4 m and reduces the worst-case RMSE across the six links from 160.9 m to 11.7 m, degrading by only 15.8% under adverse channel conditions versus 31.5% for the standard Kalman filter. These results indicate that explicit minimax-robust, environment-aware filtering is a theoretically grounded and practically inexpensive route to uncertainty-aware indoor localization.
Downloads
Downloads
Published
Issue
Section
License
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.

